10 给予scrapy-redis的分布式爬虫

1. 安装

　　pip install scrapy_redis

2. 爬虫文件

　　scrapy-redis提供了两种爬虫

　　

from scrapy_redis.spiders import RedisSpider


class MySpider(RedisSpider):
    """Spider that reads urls from redis queue (myspider:start_urls)."""
    name = 'myspider_redis'
    redis_key = 'myspider:start_urls'

    def __init__(self, *args, **kwargs):
        # Dynamically define the allowed domains list.
        domain = kwargs.pop('domain', '')
        self.allowed_domains = filter(None, domain.split(','))
        super(MySpider, self).__init__(*args, **kwargs)

    def parse(self, response):
        return {
            'name': response.css('title::text').extract_first(),
            'url': response.url,
        }

from scrapy.spiders import Rule
from scrapy.linkextractors import LinkExtractor

from scrapy_redis.spiders import RedisCrawlSpider


class MyCrawler(RedisCrawlSpider):
    """Spider that reads urls from redis queue (myspider:start_urls)."""
    name = 'mycrawler_redis'
    redis_key = 'mycrawler:start_urls'

    rules = (
        # follow all links
        Rule(LinkExtractor(), callback='parse_page', follow=True),
    )

    def __init__(self, *args, **kwargs):
        # Dynamically define the allowed domains list.
        domain = kwargs.pop('domain', '')
        self.allowed_domains = filter(None, domain.split(','))
        super(MyCrawler, self).__init__(*args, **kwargs)

    def parse_page(self, response):
        return {
            'name': response.css('title::text').extract_first(),
            'url': response.url,
        }

3. settings配置

　　使用redis_spider组件中封装好的管道　　ITEM_PIPELINES = { 'scrapy_redis.pipelines.RedisPipeline': 400 }　　

　　# 使用scrapy-redis组件的去重队列 DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"

　　# 使用scrapy-redis组件自己的调度器 SCHEDULER = "scrapy_redis.scheduler.Scheduler"

　　# 是否允许暂停 SCHEDULER_PERSIST = True

　　

　　REDIS_HOST = 'redis服务的ip地址'

　　REDIS_PORT = 6379

　　REDIS_ENCODING = ‘utf-8’

　　REDIS_PARAMS = {‘password’:’123456’}

4. 开启redis-server 和 redis-cli

5. scrapy runspider myspider.py 开启分布式爬虫

6. 向调度器中扔入一个起始url, lpush redis_key url